Instructions to use h94/IP-Adapter-FaceID with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use h94/IP-Adapter-FaceID with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("h94/IP-Adapter-FaceID", dtype=torch.bfloat16, device_map="cuda") prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k" image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
- Local Apps
- Draw Things
- DiffusionBee
What is difference between "IP-Adapter-FaceID" and "plus-face-sdxl" , " pluse-face_sd15" models
#1
by yash16 - opened
What is difference between "IP-Adapter-FaceID" and "plus-face-sdxl" , " pluse-face_sd15" models
one use face id embedding, another use CLIP image embedding
Which things result in better quality?
the two is some different, one is good at keeping id consistency, another is good at keep face structure, and in fact you use both to get better results.
how to properly run it in a1111? maybe tutorial?
When will the model for SDXL released?
do it run in a1111. gona be that guy but am having trouble finding information on getting it working properly.
it not supported now